© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45699
    Prev
    Next
    INDEX
    Explanations

    corrections to papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Примечание
    -0.91
    Дополнитель
    -0.78
     резулта
    -0.77
    adaptador
    -0.76
     mere
    -0.75
    providecommand
    -0.74
     ทรง
    -0.74
    productName
    -0.74
    了承
    -0.74
     farol
    -0.74
    POSITIVE LOGITS
    Ski
    0.88
     часть
    0.84
     gespe
    0.80
     schema
    0.80
    🛌
    0.79
     table
    0.76
     الخدم
    0.76
     техни
    0.76
    жур
    0.76
    rese
    0.74
    Activations Density 0.002%

    No Known Activations